- Experience
- 3+ yrs
- Salary
- —
- Openings
- 1
- Posted
- 3 days ago
- Work mode
- In office
- Resume
- Required to apply
Where you'll work
Sign in to tell us what does and doesn't work for you here — it sharpens every match we show you.
Job description
About the Role
Our client, an expanding Industrial AI firm in Munich, Germany, seeks a Machine Learning Engineer to build and deploy ML models targeting forecasting, anomaly detection, and operational process enhancement. This position involves handling the entire ML pipeline—from data investigation and model creation to deployment and ongoing improvements—working on AI solutions addressing genuine industrial challenges.
Responsibilities
- Create and train machine learning models utilizing Python and PyTorch.
- Develop solutions focused on forecasting and anomaly detection.
- Construct models aimed at operational and process optimization.
- Analyze and preprocess structured and time-series datasets.
- Design feature engineering and data processing pipelines.
- Assess model performance through suitable metrics and experimental validation.
- Deploy and integrate models into software systems for production use.
- Manage experiment tracking and version control using MLflow.
- Package ML tasks with Docker containers.
- Run and maintain ML services on AWS infrastructure.
- Monitor deployed models and enhance their performance continuously.
- Work closely with Data, Software, and Product teams to develop ML-driven solutions for operational issues.
Required Skills
- Minimum three years of experience in Machine Learning Engineering, Applied ML, Data Science, or related roles with production deployment background.
- Proficiency in Python programming and PyTorch framework.
- Familiarity with scikit-learn for machine learning tasks.
- Knowledge of SQL for data querying.
- Experience with Docker for containerization.
- Hands-on use of AWS cloud services for ML deployments.
- Competence with MLflow for experiment and model lifecycle management.
Preferred Qualifications
- Exposure to time-series modeling and forecasting techniques.
- Experience in anomaly detection and optimization methods.
- Skills in using XGBoost or LightGBM libraries.
- Knowledge of Pandas and NumPy for data manipulation.
- Familiarity with FastAPI framework.
- Understanding of Kubernetes and Airflow for orchestration.
- Competence in monitoring models post-deployment.
- Background in IoT, sensor data, or industrial/manufacturing systems advantageous.